LLM Digest

Story

arxiv_cs_cl · Oct 27, 2026 · paper

Source brief

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

arxiv.orgOct 27, 2026
original source linked

In brief

Long-term memory enables Large Language Models (LLMs) to maintain coherent and personalized interactions across extended conversations. However, existing memory systems face two key challenges: (1) Information Entangl...

Feed lens

agenteval

Read the original at arxiv.org →Open in live feed Read that day’s brief

ETAMem: Decoupling and Aligning Heterogeneous Memory for Long-Term Conversational Agents

Earlier in this thread 4 items

AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory

UTILMEM: Benchmarking Evidence Utilization in Long-Term Conversational Memory

Beyond Context Windows: Evaluating Long-Term Memory for AI Agents

FTA-Mem: Fact-Time-Affect Anchored Memory for Low-Density Long-Term Dialogue